Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    list of examples or approaches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    驚
    0.73
    something
    0.71
     Stable
    0.65
    เชิง
    0.65
     weaning
    0.64
     Swal
    0.64
    馬
    0.63
    bringing
    0.63
     الكامل
    0.63
    獣
    0.62
    POSITIVE LOGITS
     toda
    0.78
     vive
    0.78
    aket
    0.77
     promove
    0.77
     todos
    0.76
     irá
    0.73
     África
    0.73
     todo
    0.73
     СССР
    0.73
     berharap
    0.72
    Act Density 0.002%

    No Known Activations